AI agents use set_multihop to create or update resources in Mullvad — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mullvad environment.
The tool modifies VPN configuration (multihop routing) rather than merely reading state or executing arbitrary operations. This is a reversible write operation—the setting can be changed back. Severity is medium because misconfiguration could disrupt user connectivity or privacy posture, but no financial or destructive consequences.
From the tool's definition Tool name 'set_multihop' indicates configuration modification of Mullvad VPN multihop setting. Sibling tools include 'connect', 'disconnect', 'get_settings', implying this server performs write operations on VPN state and settings.
Attacks that exploit this kind of access
set_multihop. It is categorised as a Write tool in the Mullvad MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mullvad MCP server in PolicyLayer and add a rule for set_multihop: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Mullvad. Nothing to install.
set_multihop is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the set_multihop rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for set_multihop. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
set_multihop is provided by the Mullvad MCP server (oresam-xyz/mullvad-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →